By 2050, the Earth’s population is expected to reach nearly 10 billion. This growth creates a tremendous demand for food resources that deliver high yields in the face of climate change, especially drought, heat, pest and disease resistant crop varieties.
Join Alphabet Inc.’s so-called “Moonshot Factory” X. Here, innovators face the world’s biggest challenges head-on and develop innovative technologies at the pace of startups. One of X’s current efforts, Project Mineral, addresses the global food security crisis through the term “computational agriculture,” coined by X to describe new technologies that further deepen our understanding of the plant world. The focus is on finding an effective way to do it.
“The agricultural industry has been digitized,” says Elliott Grant, a leader in project minerals. Today’s farmers use sensors, GPS, and spreadsheets to collect data about their crops and generate satellite images of their fields. “But that hasn’t led to more understanding. Therefore, the next step beyond digitization is to combine multiple technologies such as robotics, sensors, data modeling, machine learning, and simulation to achieve this very high level. It’s a science that understands the complex world of plants. The subtle difference is that computational agriculture is a sense-making of all data, “Grant explains.
Since the project started in 2016, mineral team innovators have focused on answering one important question. Is it possible to teach machines to understand the world of plants?
A sleek four-wheeled plant rover is as tall as a shipping container and as wide as a car. (X, Moonshot Factory)
After years of tweaking, Grant and his team’s latest prototype (a robot like a plant-scan rover with artificial intelligence) will make its public debut at the Smithsonian’s “Future” exhibition. It’s arts, history, and design and technology opened later this year at the Arts & Industries Building in Washington, DC. A sophisticated four-wheeled plant rover that can be synchronized with satellite imagery, weather data, and soil information, is as tall as a shipping container, as wide as a car, and uses a variety of camera and mechanical algorithms. The plant. As you roll over the farmland, you can identify weeds, measure fruit ripeness, and predict crop yields. Mineral rover can also be adjusted in width, length and height to accommodate crops of different stages of development. For example, you can be taller to image a towering mature wheat plant, or wider to scan a large bed of lettuce.
But it wasn’t that chic and impressive. The first prototype was created on two bikes, some scaffolding, a roll of duct tape, and some Google Pixel smartphones. Can a diverse team of minerals, consisting of engineers, biologists, agronomists, etc., take them to a nearby strawberry field and pull a row of red fruits to capture enough plant images to test the Franken machine? I checked. Used for machine learning.
“So, after pushing and pulling this contradiction for hours through a bunch of mud and crushed berries, we went back to the lab and saw the images we had, and there were still hundreds. I conclude that there is a glimpse of the need for improvement and hope that this will work, “Grant explains.
The first prototype was created on two bikes, some scaffolding, a roll of duct tape, and some Google Pixel smartphones. (X, Moonshot Factory)
After their first experiment, and discussions with farmers and plant breeders, the mineral team created, discarded, and reimagined their rover. This Burn and Churn momentum building phase is part of X’s rapid iteration. If the experiment goes wrong, the X project leader learns from the error and moves on. “The essence of rapid iteration is to act quickly, take risks, and take wise risks, but we do it in a way that leads to continuous learning,” says Grant.
In one experiment, minerals used a machine learning algorithm called CycleGAN, or a cycle-generating hostile network, to see if they could create simulated plant images of strawberries. CycleGAN produces realistic images that Mineral can use to diversify Rover’s image library. In this way, when Rover encounters different scenarios in the field, he can pinpoint a particular crop, characteristic, or disease.
Such AI helps to simulate plant diseases, pests and pathogens. This is especially useful when the robot needs to recognize something it has never seen before. (This approach prevents the harmful alternative of deliberately inoculating the fields.)
“You can create simulated images of plants that are realistic enough to be used for training your model. [artificial neural network or computing system]Even if you’ve never seen the plant in the real world, “Grant explains.
Mineral rover can identify weeds from crops, which allows farmers to use less chemicals to keep weeds away. (X, Moonshot Factory)
Ultimately, the team built a rover sophisticated enough to detect rust and other phytofungal diseases. Mineral has partnered with a Filipino farmer to help the team develop ways to catch banana disease. Images of diseased bananas are used to teach Rover how to detect diseases that are harmful to banana crops, such as nitrogen deficiency, Panama disease, and black sigatoka.
The robot also takes an image of the flower and uses a machine learning model to count the flowering rate of the plant. This is essential to understanding how plants react to the environment and to predict how much fruit they will produce. In this way, Rover can also count the individual shoots of raspberry wands and estimate the number of soybeans in the field. So far, minerals have experimented with imaging soybeans, strawberries, melons, oil seeds, lettuce, oats, and barley, from early spouts to fully grown produce.
Rover can estimate the number of soybeans in the field. (X, Moonshot Factory)
Through the algorithm, the robot can check the size of various leaves and detect green. Rover takes pictures of plants from different angles and converts each image pixel into data. When analyzing plant colors, minerals use both RGB (red, green, blue) and HSV (hue saturation) color coding.
“If you find that a plant has a particular shade of green, it helps you predict how much yield you’ll get,” explains Olivia Evans, marketing manager at X. “And that’s something people can’t do objectively because we all see colors differently. Machines using RGB color coding, hue saturation coding, etc. see it objectively. And can detect those patterns. “
In addition to farmers managing their crops, plant breeders spend hours manually documenting the physical properties of thousands of plants throughout the field, a process known as the phenotype. .. However, the collection of phenotypic data depends on human perception, and human perception is not always accurate.
“Can we develop a set of technical tools to provide these breeders with a new way to see the world of plants more faithfully, more often and more easily? “Grant says. “Passing through fields and phenotypic plants is a very tedious task.”
Here, Rover counts rapeseed flowers and buds. (X, Moonshot Factory)
Meanwhile, scientists are rapidly working to learn more about plant genes and their genotypes and to match these genetic characteristics with the physical and phenotypes of plants. In the agricultural world, this missing information about how genes are associated with desirable traits is known as a phenotypic bottleneck. By understanding how plant traits are represented and combining them with logs of available gene sequences, scientists breed more robust plants ready to face climate change challenges. You can.
It takes time to bring new crops to market. Due to the vast amount of genetic and phenotypic data to analyze, it takes time to understand how these genes are expressed through plant properties and environmental responses.
“Because we don’t know what’s happening in this area, we can’t really look at the genome to find out which genes are responsible for drought resistance, nitrogen deficiency, or resistance to certain diseases,” he said. Founder Chinmay Soman explains. CEO of EarthSense, an agricultural technology company working on similar rover technology. “That is, everything starts with a high-throughput field phenotype.”
Computer vision is becoming a solution to phenotypic bottlenecks, as AI can derive plant information from simple photographs. EarthSense’s Terra Sentia is a rugged robot that fits in the trunk of a car and is small enough to be zipped under the canopy of a plant, while Mineral’s rover rises above the crop and retrieves data from above. You need a truck to transport it. Both employ AI, and collecting data on plant characteristics will enable crop breeders to develop crop varieties more effectively and efficiently. Mineral rover takes thousands of photos per minute. That’s more than 100 million images in a season.
Project Mineral’s Rover has come a long way from the origin of cobblestones, but it’s still a prototype. Despite all the techniques, minerals emphasize that they are constantly improving and working closely with agricultural experts to better understand the plant.
“Rover can be thought of as the current embodiment of the vision we designed for breeders, and we are learning with them,” says Grant.
In “Futures”, the prototype will be exhibited in the “Futures that Work” part of the exhibition in the West Hall of AIB. This space was created to reflect updatableness and sustainability and to showcase various innovations that may soon be available.
Ashley Morese, a special project curator at the Smithsonian Arts and Industries Building, said: “As you know, it’s not necessarily something that unfolds from the machine shop floor, but it’s beyond that stage of early prototyping, and there’s still a lot of twist to solve.”
The video behind the rover display shows Mineral Rover’s fleet roaming the field before switching to footage of what Rover saw while filming strawberries, soybeans, and melons.
“There’s something a bit anamorphic in that the camera is like the eyes you’re looking forward to,” says Molese. “I want to know how visitors react to it.”
Within the space, visitors can inspect mineral plant rover, imagine the future of food sustainability and safety, and think about all “what if” as well as the mineral team.
“What if the farmer could manage all the plants individually? What would it do for sustainability? What if the disease could be detected before it became visible? Or symbiotic So what if we could grow together plants with less input and healthier plants? These are what get us up every day, ”says Grant.
The mention sources can contact us to remove/changing this article
What Are The Main Benefits Of Comparing Car Insurance Quotes Online
LOS ANGELES, CA / ACCESSWIRE / June 24, 2020, / Compare-autoinsurance.Org has launched a new blog post that presents the main benefits of comparing multiple car insurance quotes. For more info and free online quotes, please visit https://compare-autoinsurance.Org/the-advantages-of-comparing-prices-with-car-insurance-quotes-online/ The modern society has numerous technological advantages. One important advantage is the speed at which information is sent and received. With the help of the internet, the shopping habits of many persons have drastically changed. The car insurance industry hasn't remained untouched by these changes. On the internet, drivers can compare insurance prices and find out which sellers have the best offers. View photos The advantages of comparing online car insurance quotes are the following: Online quotes can be obtained from anywhere and at any time. Unlike physical insurance agencies, websites don't have a specific schedule and they are available at any time. Drivers that have busy working schedules, can compare quotes from anywhere and at any time, even at midnight. Multiple choices. Almost all insurance providers, no matter if they are well-known brands or just local insurers, have an online presence. Online quotes will allow policyholders the chance to discover multiple insurance companies and check their prices. Drivers are no longer required to get quotes from just a few known insurance companies. Also, local and regional insurers can provide lower insurance rates for the same services. Accurate insurance estimates. Online quotes can only be accurate if the customers provide accurate and real info about their car models and driving history. Lying about past driving incidents can make the price estimates to be lower, but when dealing with an insurance company lying to them is useless. Usually, insurance companies will do research about a potential customer before granting him coverage. Online quotes can be sorted easily. Although drivers are recommended to not choose a policy just based on its price, drivers can easily sort quotes by insurance price. Using brokerage websites will allow drivers to get quotes from multiple insurers, thus making the comparison faster and easier. For additional info, money-saving tips, and free car insurance quotes, visit https://compare-autoinsurance.Org/ Compare-autoinsurance.Org is an online provider of life, home, health, and auto insurance quotes. This website is unique because it does not simply stick to one kind of insurance provider, but brings the clients the best deals from many different online insurance carriers. In this way, clients have access to offers from multiple carriers all in one place: this website. On this site, customers have access to quotes for insurance plans from various agencies, such as local or nationwide agencies, brand names insurance companies, etc. "Online quotes can easily help drivers obtain better car insurance deals. All they have to do is to complete an online form with accurate and real info, then compare prices", said Russell Rabichev, Marketing Director of Internet Marketing Company. CONTACT: Company Name: Internet Marketing CompanyPerson for contact Name: Gurgu CPhone Number: (818) 359-3898Email: [email protected]: https://compare-autoinsurance.Org/ SOURCE: Compare-autoinsurance.Org View source version on accesswire.Com:https://www.Accesswire.Com/595055/What-Are-The-Main-Benefits-Of-Comparing-Car-Insurance-Quotes-Online View photos
to request, modification Contact us at Here or [email protected]